To Örebro University

oru.seÖrebro University Publications
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Dynamic Threshold Based Approach for Detecting the Test Limits
Örebro University, School of Science and Technology. (Computer Science)ORCID iD: 0000-0003-3054-0051
Product Development Unit, Cloud RAN, Integration and Test, Ericsson AB, Stockholm, Sweden; Technical University of Berlin, Germany.
Product Development Unit, Cloud RAN, Integration and Test, Ericsson AB, Stockholm, Sweden; M¨alardalen University, Product Realization, School of Innovation, Design and Engineering, Eskilstuna, Sweden.ORCID iD: 0000-0002-8724-9049
2021 (English)In: Sixteenth International Conference on Software Engineering Advances (ICSEA 2021) / [ed] Lugi Lavazza; Hironori Washizaki; Herwig Mannert, International Academy, Research, and Industry Association (IARIA) , 2021, p. 71-80Conference paper, Published paper (Refereed)
Abstract [en]

Finding a balance between meeting the testing goals and testing resources is always a challenging task. Therefore, employing Machine Learning (ML) techniques for test optimization purposes has received a great deal of attention. However, utilizing ML techniques requires frequently large volumes of data to obtain reliable results. Since the data gathering is hard and also expensive, reducing unnecessary failure or retest in a testing process might end up minimizing the testing resources. Final test yield is a proper performance metric to measure the potential risks influencing certain failure rates. Typically, production determines the yield’s minimum threshold based on an empirical value given by the subject matter experts. However, those thresholds cannot monitor the yield’s fluctuations beyond the acceptable thresholds, which might cause potential failures in consecutive tests. Furthermore, defining the empirical thresholds as either too tight or too loose in production is one of the main causes of yield dropping in the testing process. In this paper, we propose an ML-based solution that detects the divergent yield points based on the prediction and raises a flag depending on the yield class to the testers when a divergent point is above a data-driven threshold. This flexibility enables engineers to have a quantifiable tool to measure to what extend the different changes in the production process are affecting the product performance and execute actions before they occur. The feasibility of the proposed solution is studied by an empirical evaluation, which has been performed on a Telecom use-case at Ericsson in Sweden and tested in two of the latest radio technologies, 4G and 5G.

Place, publisher, year, edition, pages
International Academy, Research, and Industry Association (IARIA) , 2021. p. 71-80
Keywords [en]
Software Testing, Test Optimization, Machine Learning, Regression Analysis, Imbalanced Learning
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-108707ISBN: 9781612088945 (print)OAI: oai:DiVA.org:oru-108707DiVA, id: diva2:1802033
Conference
The Sixteenth International Conference on Software Engineering Advances (ICSEA 2021), Barcelona, Spain, October 3-7, 2021
Funder
Vinnova, D_RODS (2023-00244)Knowledge Foundation, 20190128Available from: 2023-10-03 Created: 2023-10-03 Last updated: 2023-10-05Bibliographically approved
In thesis
1. AI-Based Methods For Improved Testing of Radio Base Stations: A Case Study Towards Intelligent Manufacturing
Open this publication in new window or tab >>AI-Based Methods For Improved Testing of Radio Base Stations: A Case Study Towards Intelligent Manufacturing
2023 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Testing of complex systems may often require the use of tailored-made solutions, expensive testing equipment, large computing capacity, and manual implementation work due to domain uniqueness. The aforementioned test resources are expensive and time-consuming, which makes them good candidates to optimize. A radio base station (RBS) is a complex system. Upon the arrival of new RBS generations, new testing challenges have been introduced that traditional methods cannot cope with. In order to optimize the test process of RBSs, product quality and production efficiency can be studied.

Despite that AI techniques are valuable tools for monitoring behavioral changes in various applications, there have not been sufficient research efforts spent on the use of intelligent manufacturing in already existing factories and production lines. The concept of intelligent manufacturing involves the whole system development life-cycle, such as design, production, and maintenance. Available literature about optimization and integration of industrial applications using AI techniques has not resulted in common solutions due to the complexity of the real-world applications, which have their own unique characteristics, e.g., multivariate, non-linear, non-stationary, multi-modal, class imbalance; making it challenging to find generalizable solutions. This licentiate thesis aims to bridge the gap between theoretical approaches and the implementation of real industrial applications. 

In this licentiate thesis, two questions are explored, namely how well AI techniques can perform and optimize fault detection and fault prediction on the production of RBSs, as well as how to modify learning algorithms in order to perform transfer learning between different products. These questions are addressed by using different AI techniques for test optimization purposes and are examined in three empirical studies focused on parallel test execution, fault detection and prediction, and automated fault localization. For the parallel test execution study, two different approaches were used to find and cluster semantically similar test cases and propose their execution in parallel. For this purpose, Levenshstein distance and two NLP techniques are compared. The results show that cluster-based test scenarios can be automatically generated from requirement specifications and the execution of semantically similar tests can reduce the number of tests by 95\% in the study case if executed in parallel. 

Study number two investigates the possibility of predicting testing performance outcomes by analyzing anomalies in the test process and classifying them by their compliance with dynamic test limits instead of fixed limits. The performance measures can be modeled using historical data through regression techniques and the classification of the anomalies is learned using support vector machines and convolutional neural networks. The results show good agreement between the actual and predicted learned model, where the root-mean-square error reaches 0.00073. Furthermore, this approach can automatically label the incoming tests according to the dynamic limits, making it possible to predict errors in an early stage of the process. This study contributes to product quality by monitoring the test measurements beyond fixed limits and contributes to making a more efficient testing process by detecting faults before they are measured. Moreover, study two considers the possibility of using transfer learning due to an insufficient number of anomalies in a single product. 

The last study focuses on root cause analysis by analyzing test dependencies between test measurements using two known correlation-based methods and mutual information to find strength associations between measurements. The contributions of this study are twofold. First, test dependencies between measurements can be found using Pearson and Spearman correlation and MI; and their dependencies can be linear or higher order. Second, by clustering the associated tests, redundant tests are found, which could be used to update the test execution sequence and choose to execute only the relevant tests, hence, making a more efficient production process by saving test time.

Place, publisher, year, edition, pages
Örebro: Örebro University, 2023. p. 34
Series
Örebro Studies in Technology, ISSN 1650-8580 ; 102
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-108714 (URN)
Presentation
2023-10-02, Örebro universitet, Prismahuset, Hörsal P1, Fakultetsgatan 1, Örebro, 13:15 (English)
Opponent
Supervisors
Funder
Knowledge Foundation, 20190128Vinnova, D-RODS (2023-00244)
Available from: 2023-10-05 Created: 2023-10-03 Last updated: 2023-10-05Bibliographically approved

Open Access in DiVA

A Dynamic Threshold Based Approach for Detecting the Test Limits(565 kB)33 downloads
File information
File name FULLTEXT01.pdfFile size 565 kBChecksum SHA-512
610cea654aa7616e727311c8f50143e601dfc5987db5afcb50933f185832df232eac0cffd59685a5ee5c164bc596495cdf08149593f57e3788e22729a673e6df
Type fulltextMimetype application/pdf

Authority records

Landin, Cristina

Search in DiVA

By author/editor
Landin, CristinaTahvili, Sahar
By organisation
School of Science and Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 33 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 313 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf